anthony_franco

Connect your coding tool to a browser (like with the playwright MCP) and just let it iterate on its own until it matches the design you want.

I agree with everything except for Kamal. I'm happy to have someone else handle the server side maintenance. Maybe once my service grows so huge that handling it myself makes sense moneywise, but starting off that way is overkill when there's such affordable alternatives.

Lightweight umbrellas.

I find that if you check when the LLM's data was updated, and then choose a framework/language version release date that's before that, then it's pretty good.

In my case I use tailwind css a lot and found that sticking to v3.4.3 created the best output from LLMs.

You built a product first and then are searching for the market for it? That's tough. If you do it in reverse, find the market first and then build a product for them, it's 100x easier. Trust me.

The llm just returns a method name and arguments to pass it. Your code is in charge of actually executing it, and then replying with an answer.

There’s some YouTubers that release weekly videos about AI news. I suggest you search around for ones that suit your interests.

Friendster was one of the first big social networks but the amount of users slowed it down. That made everyone move over to MySpace/Facebook.

If I remember right, Friendster had a feature that told you how you were connected to every other person (friend of a friend of a friend, etc.). And it was this feature that made the pages slow to load.

The 4-Hour Workweek - motivated me to start my own business and now I have a lot of flexibility in my life.

http://bookmooch.com/

It's a great way to trade your books with others. And you can pick and choose from others' collections. Plus it's a good way to get rid of any extra books you have lying around.

I setup mine to automatically restart every night and it fixed a lot of issues.

I had the first one Venmo me just to verify people are willing to pay. Then I setup a quick solution using a no-code platform.

Maybe down the line I’ll build a fully custom one but for now it’s been working great.

Well, did you improve the product based on what the "free candy" people said? Were you able to determine the reasons they didn't buy and then improve your product accordingly?

Seems you should be improving your product/product positioning more. That would make marketing a lot easier.

I reached out to my friends to email-intro me to anyone who might be interested in my product. That mutual connection made it so that people were way more willing to jump on a call to discuss the problem space.

I made sure to be respectful and mindful of their time on each interview call. At the end of the call I asked them to refer me to anyone else that might be interested too. That way, the number of potential interviewees kept growing.

Eventually we did enough phone interviews to be confident to proceed with the development.

Amazon directly competes with Netflix and they get along fine.

https://aws.amazon.com/solutions/case-studies/netflix/

Reach out to your network or email your friends to put you in contact with potential users. It should be moderately easy since you're just asking for a free Skype call, you're not asking for money yet.

If you're having problem finding people to get on a free Skype call then it's a big red flag. You'll need to reconsider your positioning or your market. Because eventually you'll (presumably) be asking for money and that's even harder.

You won't get enough data if you ask them to fill out a survey. If you try a single interview you'll see why. You'll end up with pages of notes and venture into problems you had no idea about. If you had asked them to fill out a survey instead, you would've ended up with just a fraction of the information.

And world wide or not doesn't matter. I did all my interviews over Skype.

Indie Hackers lists lots of examples you can read about. Just filter on employee count and revenue: https://www.indiehackers.com/interviews/page/1?employeeCount...

First step is to validate the problem. Ask 20 people in your target market about their biggest problems. If they bring up the problem early in the conversation, you know you got a winner. If you gotta pull it out of them, you'll have trouble getting them to use whatever solution you come up with.

Then you brainstorm on a solution based on the notes from the interviews.

Then you interview another 20 people and pitch the idea to them. At least half of them should seem excited about it. If not, you gotta either rethink the solution or the problem.

And if you can't find 40 people to interview, that's another problem altogether.

Good luck!

“How to Win Friends and Influence People” is a good one.

It’s a nice reminder on how to treat people.

First piece of advice is to get it in front of potential users ASAP (if you haven't yet). Just to make sure you're going in the right direction. Even just mockups or wireframes is good enough (we started off showing hand-drawn designs at the very beginning).

And secondly, if you want to speed things up I'd look into hiring a developer in Eastern Europe through Upwork. That's what I did and I wish I'd done it a lot sooner.

Happy to talk more. I built my startup on the side and now it support me full-time. Good luck!

Pretty much all businesses are automatable. Just hire good people and have good processes in place for them to follow.

For example, WP Curve was even able to automate the process of hiring dozens of developers. You would've that that it would require a very manual intervention by the owner: https://wpcurve.com/hiring-developers/

500-1M USD? If you hire full-time US workers then that's probably the case.

For me I hired a few remote part-timers around the world. So it costs me an order of magnitude less. And they're all awesome, so I barely have to lift a finger.

Start any business and just hire good people to run it for you.

I have a SaaS. I have a support person, product manager, and developer. Between them they handle 90% of the day to day tasks.

I could write a whole book on what I’ve learned :) As can any other business owner I think. But I’d be happy to chat with anyone wanting advice.

Every business can be automated. Just find good people to run it for you.

If you interview people about the type of problems they deal with day to day then you start to get tons of ideas. That’s how I started.

I started a SaaS company in the hospitality industry.

It took me about four years. It would've been faster if I knew then what I know now.

The 4-Hour Workweek - made me quit my job and start a business. Since then I've been able to travel internationally for the first time in my life while working as much as I want.